研究生: |
連偉丞 WEI-CHENG LIAN |
---|---|
論文名稱: |
基於影像縫合之自主停車路徑規劃與實現 Autonomous Parking Path Planning and Implementation Based on Stitched Images |
指導教授: |
郭重顯
Chung-Hsien Kuo |
口試委員: |
劉益宏
蘇順豐 翁慶昌 |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2021 |
畢業學年度: | 109 |
語文別: | 英文 |
論文頁數: | 70 |
中文關鍵詞: | 環景影像 、自動停車 、PSO 、Reeds Shepp 曲線 |
外文關鍵詞: | Stitched image, Automatic parking, Particle Swarm Optimization, Reeds Shepp curve |
相關次數: | 點閱:169 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
自動停車主要可分為路徑規劃與車輛定位,其中大多數停車路徑規劃為建立柵格地圖後進行路徑規劃,對於狹窄的停車區域可能會因為柵格地圖的解析度不夠導致不一定規劃的出路徑,而車輛定位使用感測器偵測周遭障礙物當作參考並建立柵格地圖若無障礙物當參考點則無法建立柵格地圖,為了解決上述本論文設計了環景影像系統控制平台及提出停車路徑規劃演算法,透過環景系統擷取地標特徵並且使用視覺影像技術來達到局部定位及環境特徵辨識,在已知車輛及停車格的位置及角度時利用Reed Shepp曲線找出車輛行駛的最短路徑並透過粒子群演算法(Particls Swarm Optimization, PSO)規劃出避障節點,此為Reeds Shepp粒子群演算法(Reeds Shepp Particls Swarm Optimization,RSPSO),並結合純追蹤演算法(Pure Pursuit algorithm)做路徑追蹤達到自動停車功能,在不同的狀態下,整體來說RSPSO的路徑長度與時間均優於同樣是利用RS曲線規劃的Hybrid A*演算法,在實作上本文設計轉向機構將一般電動搬運車改裝成無人搬運車以及架設大範圍且精準的環景系統,並達到能夠在室外自動停車,其結果顯示本論文能夠透過一般的IP攝影機架設環景影像系統,並能夠在戶外環境下定位及影像控制停車。
Automatic parking system consists of two parts: path planning and vehicle positioning. As most of the path planning methods, a grid map firstly establishes for planning the path, however, insufficient resolution has a risk in planning a certain path for narrow parking area. And vehicle positioning implements multiple sensors to detect surroundings obstacles as a reference to build a grid map. If there is no obstacle as a reference, a grid map cannot be established. To solve the aforementioned problems, this thesis designed a stitched images system control platform and proposed an algorithm for parking path planning. Stitched images system captures the features of the landmarks. Moreover, the visual imaging technology is used to achieve local positioning and environment features identification. In this thesis, Reeds Shepp Particle Swarm Optimization (RSPSO) algorithm is proposed, which the Reeds Shepp (RS) curve is used to find the shortest path for vehicle driving when the position and , yaw angle of vehicle, and parking grid are known. And the Particle Swarm Optimization (PSO) is used to planning the obstacle avoidance nodes. In addition, combing with Pure Pursuit algorithm for path tracking, the automatic parking can be achieved. Under different scenarios, the overall path planning length and planning time of proposed RSPSO are better than Hybrid A* algorithm, which is also planned by RS curve. This thesis designs a steering mechanical to transform a general electric truck into an unmanned electric truck, and installs a large-scale and accurate surrounding view system to achieve automatic parking for outdoor used. The results show that this thesis can achieve stitched images through a general IP camera, and can successfully positioning and eventually accomplish a self-parking in the outdoor environment.
Keywords — Stitched image, Automatic parking, Particle Swarm Optimization, Reeds Shepp curve.
[1] J. Lee, M. Kim, S. Lee, and S. Hwang, “Real-Time Downward View Generation of a Vehicle Using Around View Monitor System,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 8, pp. 3447-3456, Aug. 2020.
[2] L. E., Dubins, “On Curves of Minimal Length with a Constraint on Average Curvature, and with Prescribed Initial and Terminal Positions and Tangents,” American Journal of Mathematics, vol. 79, no. 3, pp. 497-516, 2021.
[3] J. A. Reeds, and L. A. Shepp, “Optimal paths for a car that goes both forwards and backwards,” Pacific journal of mathematics, vol. 145.2, pp. 367-393, 1990.
[4] J. M. Kim, K. I. Lim, and J. H. Kim, “Auto parking path planning system using modified Reeds-Shepp curve algorithm,” International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp. 311-315, 2014.
[5] A. Gupta, R. Divekar, and M. Agrawal, “Autonomous parallel parking system for Ackerman steering four wheelers,” IEEE International Conference on Computational Intelligence and Computing Research, pp. 1-6, 2010.
[6] Z. Lv, L. Zhao, and Z. Liu, “A Path-Planning Algorithm for Automatic Parallel Parking,” International Conference on Instrumentation, Measurement, Computer, Communication and Control, pp. 474-478, 2013.
[7] H. Vorobieva, S. Glaser, N. Minoiu-Enache and S. Mammar, “Automatic Parallel Parking in Tiny Spots: Path Planning and Control,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 1, pp. 396-410, Feb. 2015.
[8] L. Wang, L. Guo, and Y. He, “Path Planning Algorithm for Automatic Parallel Parking from Arbitrary Initial Angle,” International Symposium on Computational Intelligence and Design (ISCID), pp. 55-58 ,2017.
[9] S. Zhang, M. Simkani, and M. H. Zadeh, “Automatic Vehicle Parallel Parking Design Using Fifth Degree Polynomial Path Planning,” IEEE Vehicular Technology Conference (VTC Fall), San Francisco, USA, pp. 1-4, 2011.
[10] Z. Liang, G. Zheng, and J. Li, “Automatic parking path optimization based on Bezier curve fitness,” IEEE International Conference on AutomationandLogistics, Zhengzhou, China, pp. 583-587, 2012.
[11] L. Li, and F. Wang, “Parking guidance system for front wheel steering vehicles using trajectory generation,” IEEE International Conference on Intelligent Transportation Systems, vol. 2, pp. 1770-1775, 2003.
[12] W. Liu, Z. Li, L. Li, and F. Wang, “Parking Like a Human: A Direct Trajectory Planning Solution,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 12, pp. 3388-3397, Dec. 2017.
[13] R. Chai, A. Tsourdos, A. Savvaris, S. Chai, and Y. Xia, “Two-Stage Trajectory Optimization for Autonomous Ground Vehicles Parking Maneuver,” in IEEE Transactions on Industrial Informatics, vol. 15, no. 7, pp. 3899-3909, July 2019.
[14] S. Ma, H. Jiang, M. Han, J. Xie, and C. Li, “Research on Automatic Parking Systems Based on Parking Scene Recognition,” in IEEE Access, vol. 5, pp. 21901-21917, 2017.
[15] J. Song, W. Zhang, X. Wu, and Q. Gao, “Automatic Perpendicular Parking Trajectory Planning and Following for Vehicle,” International Conference on Electronic Information Technology and Computer Engineering (EITCE), pp. 932-935, 2019.
[16] S. Sedighi, D. Nguyen, and K. Kuhnert, “Implementation of a Parking State Machine on Vision-Based Auto Parking Systems for Perpendicular Parking Scenarios,” International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1711-1716, 2019.
[17] Y. W. Jeong, H. Wook Heo and C. C. Chung, "A Local Path Planning for Perpendicular Parking in Limited Parking Spaces," International Conference on Control, Automation and Systems (ICCAS), pp. 38-40, 2020.
[18] L. Li, C. Li, Q. Zhang, T. Guo, and Z. Miao, “Automatic parking slot detection based on around view monitor (AVM) systems,” International Conference on Wireless Communications and Signal Processing (WCSP), pp. 1-6, 2017.
[19] Z. Zhang, “A flexible new technique for camera calibration,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1330-1334, Nov. 2000.
[20] D. Dologov, S. Thrun, M. Montemerlo, and J. Diebel, “Practical search techniques in path planning for autonomous driving,” Ann Arbor, pp. 18-80, 2008.
[21] A. Scheuer and C. Laugier, “Planning sub-optimal and continuous-curvature paths for car-like robots,” Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190), vol. 1, pp. 25-31, 1998.